© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14848
    Prev
    Next
    INDEX
    Explanations

    words related to different forms of 'char' and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "Char" and variations

    np_acts-logits-general · gemini-2.0-flash

    charroux and chartists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.77
    ///<
    -0.73
     égard
    -0.73
    CloseOperation
    -0.72
    etheless
    -0.70
     سكانية
    -0.70
    erover
    -0.69
    RegistryLite
    -0.69
    hlungen
    -0.69
    ➟
    -0.68
    POSITIVE LOGITS
     CHAR
    0.76
     Char
    0.74
    Char
    0.74
    CHAR
    0.71
     chars
    0.64
     char
    0.63
     Charle
    0.61
    char
    0.60
    Composable
    0.51
     Schar
    0.51
    Activations Density 0.062%

    No Known Activations